SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.04727 · 2020

Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering

arXiv · PDF · Open in the Atlas

Code that ran

10 of 21 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 3 failures of our instrument; 11 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2006.04727.json · badge: /api/ran/2006.04727.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
HerreraKrachTeichmann/ControlledODERNN canonical (classifier label)
classifier basis: census
9 ran · 11 no recorded run
HerreraKrachTeichmann/NJODE canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_KL_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
HerreraKrachTeichmann/ControlledODERNN/GRU_ODE_Bayes/models_gru_ode_bayes.py
code served (permissive licence) · get_code("3538a026b3686dc4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

batch_size = 2
feature_dim = 4

# p_obs: predicted observations, shape (batch_size, 2 * feature_dim)
# Since it gets chunked into 2 parts (mean and var), it needs to have 2 * feature_dim in dim 1
p_obs = torch.randn(batch_size, 2 * feature_dim)

# X_obs: observed data, shape (batch_size, feature_dim)
X_obs = torch.randn(batch_size, feature_dim)

# M_obs: mask for observations, shape (batch_size, feature_dim)
M_obs = torch.ones(batch_size, feature_dim)

# obs_noise_std: observation noise standard deviation (scalar)
obs_noise_std = 0.01

# logvar: whether variance is in log space
logvar = True

ARGS = {
    'p_obs': p_obs,
    'X_obs': X_obs,
    'M_obs': M_obs,
    'obs_noise_std': obs_noise_std,
    'logvar': logvar
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_binary_CE_loss Ran
ran on a synthesized input
HerreraKrachTeichmann/ControlledODERNN/latent_ODE/likelihood_eval_LODE.py
code served (permissive licence) · get_code("c9b91f3a93d08f8c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

def get_device(tensor):
    return tensor.device

# Create label_predictions: shape (2, 4) - 2 trajectory samples, 4 predictions
label_predictions = torch.randn(2, 4)

# Create mortality_label: shape (4,) - 4 labels with some 0s and 1s
mortality_label = torch.tensor([0.0, 1.0, 0.0, 1.0])

ARGS = {
    "label_predictions": label_predictions,
    "mortality_label": mortality_label,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_loss Ran
ran on a synthesized input
HerreraKrachTeichmann/ControlledODERNN/NJODE/models.py
code served (permissive licence) · get_code("12d22dac3d5ee45c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Set up tensor dimensions: batch_size=2, feature_dim=4
batch_size = 2
feature_dim = 4

# X_obs: true X values at observations, shape (batch_size, feature_dim)
X_obs = torch.randn(batch_size, feature_dim)

# Y_obs: predicted values at observation, shape (batch_size, feature_dim)
Y_obs = torch.randn(batch_size, feature_dim)

# Y_obs_bj: predicted values before the jump, shape (batch_size, feature_dim)
Y_obs_bj = torch.randn(batch_size, feature_dim)

# n_obs_ot: number of observations over timeline for each batch element
# shape (batch_size,) with positive values
n_obs_ot = torch.tensor([3.0, 5.0])

# M_obs: observation mask, same shape as X_obs with 0s and 1s
M_obs = torch.randint(0, 2, (batch_size, feature_dim), dtype=torch.float32)

ARGS = {
    'X_obs': X_obs,
    'Y_obs': Y_obs,
    'Y_obs_bj': Y_obs_bj,
    'n_obs_ot': n_obs_ot,
    'batch_size': batch_size,
    'eps': 1e-10,
    'weight': 0.5,
    'M_obs': M_obs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_loss_2 Ran
ran on a synthesized input
HerreraKrachTeichmann/ControlledODERNN/NJODE/models.py
code served (permissive licence) · get_code("b5eeaff03e06c051")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
feature_dim = 4

# X_obs: observed X values, shape (batch_size, feature_dim)
X_obs = torch.randn(batch_size, feature_dim)

# Y_obs: observed Y values, shape (batch_size, feature_dim)
Y_obs = torch.randn(batch_size, feature_dim)

# Y_obs_bj: another observed Y variant, shape (batch_size, feature_dim)
Y_obs_bj = torch.randn(batch_size, feature_dim)

# n_obs_ot: number of observations, shape (batch_size,)
n_obs_ot = torch.ones(batch_size)

# M_obs: optional mask, shape (batch_size, feature_dim)
M_obs = torch.ones(batch_size, feature_dim)

ARGS = {
    'X_obs': X_obs,
    'Y_obs': Y_obs,
    'Y_obs_bj': Y_obs_bj,
    'n_obs_ot': n_obs_ot,
    'batch_size': batch_size,
    'eps': 1e-10,
    'weight': 0.5,
    'M_obs': M_obs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gaussian_KL Ran
ran; our contract draft was wrong, not the code
HerreraKrachTeichmann/ControlledODERNN/GRU_ODE_Bayes/models_gru_ode_bayes.py
code served (permissive licence) · get_code("d7007fe42b0a49b2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

mu_1 = torch.randn(2, 4)
mu_2 = torch.randn(2, 4)
sigma_1 = torch.abs(torch.randn(2, 4)) + 0.1  # Ensure positive
sigma_2 = torch.abs(torch.randn(2, 4)) + 0.1  # Ensure positive

ARGS = {
    'mu_1': mu_1,
    'mu_2': mu_2,
    'sigma_1': sigma_1,
    'sigma_2': sigma_2
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_comparison_times_ind Ran
ran on a synthesized input
HerreraKrachTeichmann/ControlledODERNN/NJODE/physionet_train.py
code served (permissive licence) · get_code("dd7dc3c87b389bb1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create valid arguments for get_comparison_times_ind
# The function expects:
# - path_t: np.array of times (floats) - should be sorted
# - times_val: np.array of times where each entry is between min(path_t) and max(path_t)

# Create path_t: a sorted array of time points
path_t = np.array([0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0])

# Create times_val: an array of times that fall within the range of path_t
# Each value should be between min(path_t) and max(path_t)
times_val = np.array([0.05, 0.25, 0.55, 0.95])

ARGS = {
    "path_t": path_t,
    "times_val": times_val,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_data_min_max Ran
ran, honoured the contract we drafted
HerreraKrachTeichmann/ControlledODERNN/latent_ODE/physionet_LODE.py
code served (permissive licence) · get_code("97cefd1ecd9fcbca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Build records as a list of tuples
# Each record contains: (record_id, tt, vals, mask, labels)
# vals shape: (time_steps, n_features)
# mask shape: (time_steps, n_features) with values 0 or 1
# tt: time values
# record_id: identifier
# labels: target labels

record_1 = (
    "record_001",
    torch.tensor([0.0, 1.0, 2.0]),  # tt: 3 time steps
    torch.tensor([[1.0, 2.0, 3.0, 4.0],
                  [5.0, 6.0, 7.0, 8.0],
                  [9.0, 10.0, 11.0, 12.0]]),  # vals: (3, 4)
    torch.tensor([[1, 1, 1, 1],
                  [1, 0, 1, 1],
                  [0, 1, 1, 0]]),  # mask: (3, 4)
    torch.tensor([0, 1])  # labels
)

record_2 = (
    "record_002",
    torch.tensor([0.0, 1.0, 2.0]),  # tt: 3 time steps
    torch.tensor([[2.0, 3.0, 4.0, 5.0],
                  [6.0, 7.0, 8.0, 9.0],
                  [10.0, 11.0, 12.0, 13.0]]),  # vals: (3, 4)
    torch.tensor([[1, 1, 1, 1],
                  [1, 1, 0, 1],
                  [1, 1, 1, 1]]),  # mask: (3, 4)
    torch.tensor([1, 0])  # labels
)

records = [record_1, record_2]

ARGS = {
    "records": records
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_ffnn Ran
ran on a synthesized input
HerreraKrachTeichmann/ControlledODERNN/NJODE/models.py
code served (permissive licence) · get_code("ac269034a4dc74f2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    'input_size': 4,
    'output_size': 3,
    'nn_desc': [
        [8, 'relu'],
        [6, 'tanh']
    ],
    'dropout_rate': 0.5,
    'bias': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_parameter_array Ran
ran; our contract draft was wrong, not the code
HerreraKrachTeichmann/NJODE/NJODE/parallel_train.py
code served (permissive licence) · get_code("6199bec38ce9b0bb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from sklearn.model_selection import ParameterGrid

# The function get_parameter_array takes a param_dict and uses ParameterGrid
# to generate all combinations of parameters. ParameterGrid expects a dict
# where values can be lists or other iterables.

param_dict = {
    'learning_rate': [0.001, 0.01, 0.1],
    'batch_size': [16, 32],
    'num_layers': [2, 3],
    'activation': ['relu', 'tanh']
}

ARGS = {
    'param_dict': param_dict
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
poisson_log_likelihood Ran
ran on a synthesized input
HerreraKrachTeichmann/ControlledODERNN/latent_ODE/likelihood_eval_LODE.py
code served (permissive licence) · get_code("8cefc622fcbe2f88")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

def get_device(tensor):
    return tensor.device

masked_log_lambdas = torch.randn(2, 4)
masked_data = torch.randn(2, 4)
indices = torch.tensor([0, 1])
int_lambdas = torch.tensor([1.5, 2.5, 3.5])

ARGS = {
    "masked_log_lambdas": masked_log_lambdas,
    "masked_data": masked_data,
    "indices": indices,
    "int_lambdas": int_lambdas,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
add_jitter Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/GRU_ODE_Bayes/data_utils_gru_ode_bayes.py
code served (permissive licence) · get_code("05fb630e81f73dab")
How it ran

no invocation recorded.

custom_collate_fn Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/GRU_ODE_Bayes/data_utils_gru_ode_bayes.py
code served (permissive licence) · get_code("4039617eeaf62d4e")
How it ran

no invocation recorded.

evaluate_model Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/NJODE/physionet_train.py
code served (permissive licence) · get_code("e7c9692657b50119")
How it ran

no invocation recorded.

evaluate_model Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/NJODE/climate_train.py
code served (permissive licence) · get_code("172c6c49b142f584")
How it ran

no invocation recorded.

gaussian_log_likelihood Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/latent_ODE/likelihood_eval_LODE.py
code served (permissive licence) · get_code("bd43eff2ee1d2449")
How it ran

no invocation recorded.

load_metadata Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/NJODE/data_utils.py
code served (permissive licence) · get_code("a809ed2bcb40ac31")
How it ran

no invocation recorded.

parse_datasets Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/latent_ODE/parse_datasets_LODE.py
code served (permissive licence) · get_code("19750a398c51a677")
How it ran

no invocation recorded.

plot_paths_from_checkpoint Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/NJODE/extras.py
code served (permissive licence) · get_code("fa93c9ef59f86197")
How it ran

no invocation recorded.

seq_collate_fn Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/GRU_ODE_Bayes/data_utils_gru_ode_bayes.py
code served (permissive licence) · get_code("c133d40e18cb7828")
How it ran

no invocation recorded.

variable_time_collate_fn Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/latent_ODE/physionet_LODE.py
code served (permissive licence) · get_code("77d551e089ce5d29")
How it ran

no invocation recorded.

variable_time_collate_fn1 Not yet run
unverified (harvested, no recorded run)
HerreraKrachTeichmann/ControlledODERNN/latent_ODE/physionet_LODE.py
code served (permissive licence) · get_code("82d3648c208e37cf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 21 samples lifted from this paper's linked repositories, 21 carry a function identity and 0 do not. Of the 21 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 18 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_data_min_max 2 other papers
1 dated earlier, 1 later
1907.03907 (2019-07)
Latent ODEs for Irregularly-Sampled Time Series
2605.17804 (2026-05)
GenTS: A Comprehensive Benchmark Library for Generative Time Series Models
compute_KL_loss 1 other paper
1 dated earlier
1905.12374 (2019-05)
GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
gaussian_KL 1 other paper
1 dated earlier
1905.12374 (2019-05)
GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Combinations of neural ODEs with recurrent neural networks (RNN), like GRU-ODE-Bayes or ODE-RNN are well suited to model irregularly observed time series. While those models outperform existing discrete-time approaches, no theoretical guarantees for their predictive capabilities are available. Assuming that the irregularly-sampled time series data originates from a continuous stochastic process, the $L^2$-optimal online prediction is the conditional expectation given the currently available information. We introduce the Neural Jump ODE (NJ-ODE) that provides a data-driven approach to learn, continuously in time, the conditional expectation of a stochastic process. Our approach models the conditional expectation between two observations with a neural ODE and jumps whenever a new observation is made. We define a novel training framework, which allows us to prove theoretical guarantees for the first time. In particular, we show that the output of our model converges to the $L^2$-optimal prediction. This can be interpreted as solution to a special filtering problem. We provide experiments showing that the theoretical results also hold empirically. Moreover, we experimentally show that our model outperforms the baselines in more complex learning tasks and give comparisons on real-world datasets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.04727")
get_code_for_paper("2006.04727")
have("2006.04727")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.04727.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.04727.svg)](https://syntology.ai/paper/2006.04727)

Connect an agent — have() is free.